Contextual Denormalization For Automatic Speech Recognition

2. The method of claim 1, wherein the speech input is captured by a microphone of the user device.

3. The method of claim 2, wherein the user device comprises a desktop computer, a laptop computer, a tablet, a smart phone, or a wearable computing device.

4. The method of claim 1, wherein the data processing hardware resides on the user device.

5. The method of claim 1, wherein the operations further comprise selecting a list of one or more denormalizers to apply to the generated raw speech recognition result based on the context metadata.

6. The method of claim 5, wherein selecting the list of the one or more denormalizers comprises modifying a default list of denormalizers by removing one or more denormalizers from the default list of denormalizers.

7. The method of claim 5, wherein selecting the list of the one or more denormalizers comprises modifying a default list of denormalizers by adding one or more denormalizers from a predefined set of denormalizers to the default list of denormalizers.

9. The method of claim 8, wherein the memory hardware resides on the user device.

10. The method of claim 1, wherein the speech recognizer executes on the data processing hardware.

11. The method of claim 1, wherein denormalizing the generated raw speech recognition result into the denormalized text is further based on user preferences for denormalizing text.

13. The user device of claim 12, wherein the speech input is captured by a microphone of the user device.

14. The user device of claim 12, wherein the user device comprises a desktop computer, a laptop computer, a tablet, a smart phone, or a wearable computing device.

15. The user device of claim 12, wherein the operations further comprise selecting a list of one or more denormalizers to apply to the generated raw speech recognition result based on the context metadata.

16. The user device of claim 15, wherein selecting the list of the one or more denormalizers comprises modifying a default list of denormalizers by removing one or more denormalizers from the default list of denormalizers.

17. The user device of claim 15, wherein selecting the list of the one or more denormalizers comprises modifying a default list of denormalizers by adding one or more denormalizers from a predefined set of denormalizers to the default list of denormalizers.

19. The user device of claim 12, wherein the speech recognizer executes on the data processing hardware.

20. The user device of claim 12, wherein denormalizing the generated raw speech recognition result into the denormalized text is further based on user preferences for denormalizing text.